東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Machine Learning Approach to Observability Analysis of High-Dimensional Nonlinear Dynamical Systems Using Koopman Operator Theory.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine Learning Approach to Observability Analysis of High-Dimensional Nonlinear Dynamical Systems Using Koopman Operator Theory./
Author:	Balakrishnan, Shara Rhagha Wardhan.
Description:	1 online resource (190 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
Contained By:	Dissertations Abstracts International84-11B.
Subject:	Theoretical mathematics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30312814click for full text (PQDT)
ISBN:	9798379498894

Machine Learning Approach to Observability Analysis of High-Dimensional Nonlinear Dynamical Systems Using Koopman Operator Theory.
Balakrishnan, Shara Rhagha Wardhan.

Machine Learning Approach to Observability Analysis of High-Dimensional Nonlinear Dynamical Systems Using Koopman Operator Theory. - 1 online resource (190 pages)

Source: Dissertations Abstracts International, Volume: 84-11, Section: B.

Thesis (Ph.D.)--University of California, Santa Barbara, 2023.

Includes bibliographical references

Nonlinear systems can be decomposed into observable and unobservable subsystems in theory, but achieving this decomposition in a data-driven framework is challenging. Koopman operators enable us to embed nonlinear dynamical systems in high-dimensional function spaces. In this thesis, we explore how the observable decomposition of linear Koopman models relates to the observable decomposition of nonlinear systems and show how this decomposition can be achieved in a data-driven setting. In a model biological soil bacterium, Pseudomonas putida, we use a deep neural network approach to learn Koopman operator representations to model the gene expression-phenotype dynamics. Using the Koopman observable decomposition, we identified 18 out of 5564 genes in Pseudomonas putida, which impact the growth phenotype of the bacterium in R2A media. We use CRISPRi for multiplexed targeted gene regulation and show that 80% of the gene targets have the predicted impact on the fitness of the bacterium. Our results provide a novel machine learning tool to detect critical states that generate desired outcomes in complex, high-dimensional nonlinear dynamical systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379498894Subjects--Topical Terms:

3173530
Theoretical mathematics.
Subjects--Index Terms:

Genotypic activityIndex Terms--Genre/Form:

542853
Electronic books.

Machine Learning Approach to Observability Analysis of High-Dimensional Nonlinear Dynamical Systems Using Koopman Operator Theory.
LDR:02657nmm a2200409K 4500 001 2360057
005 20230925052812.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379498894
035 $a (MiAaPQ)AAI30312814
035 $a AAI30312814
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Balakrishnan, Shara Rhagha Wardhan. $3 3700669
245 1 0 $a Machine Learning Approach to Observability Analysis of High-Dimensional Nonlinear Dynamical Systems Using Koopman Operator Theory.
264 0 $c 2023
300 $a 1 online resource (190 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
500 $a Advisor: Yeung, Enoch; Hespanha, Joao.
502 $a Thesis (Ph.D.)--University of California, Santa Barbara, 2023.
504 $a Includes bibliographical references
520 $a Nonlinear systems can be decomposed into observable and unobservable subsystems in theory, but achieving this decomposition in a data-driven framework is challenging. Koopman operators enable us to embed nonlinear dynamical systems in high-dimensional function spaces. In this thesis, we explore how the observable decomposition of linear Koopman models relates to the observable decomposition of nonlinear systems and show how this decomposition can be achieved in a data-driven setting. In a model biological soil bacterium, Pseudomonas putida, we use a deep neural network approach to learn Koopman operator representations to model the gene expression-phenotype dynamics. Using the Koopman observable decomposition, we identified 18 out of 5564 genes in Pseudomonas putida, which impact the growth phenotype of the bacterium in R2A media. We use CRISPRi for multiplexed targeted gene regulation and show that 80% of the gene targets have the predicted impact on the fitness of the bacterium. Our results provide a novel machine learning tool to detect critical states that generate desired outcomes in complex, high-dimensional nonlinear dynamical systems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Theoretical mathematics. $3 3173530
650 4 $a Bioengineering. $3 657580
650 4 $a Computer engineering. $3 621879
650 4 $a Electrical engineering. $3 649834
653 $a Genotypic activity
653 $a Koopman operator theory
653 $a Machine learning
653 $a Nonlinear dynamical systems
653 $a Observability
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0642
690 $a 0202
690 $a 0544
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of California, Santa Barbara. $b Electrical & Computer Engineering. $3 1020566
773 0 $t Dissertations Abstracts International $g 84-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30312814 $z click for full text (PQDT)